# Swimm3R: Splatting with Medium-aware SfM for Underwater 3D Reconstruction

arXiv: https://arxiv.org/abs/2608.00950 · HTML: https://mlsanity.com/paper/2608.00950/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 45 references that are in the map.
- First posted on arXiv 2 Aug 2026.

## Builds on (most cited first, 27 of 27)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [3D Reconstruction with Spatial Memory](https://mlsanity.com/paper/2408.16061/) (2024)
- [3D Gaussian Splatting as Markov Chain Monte Carlo](https://mlsanity.com/paper/2404.09591/) (2024)
- [Fast Underwater Image Enhancement for Improved Visual Perception](https://mlsanity.com/paper/1903.09766/) (2019)
- [MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion](https://mlsanity.com/paper/2409.19152/) (2024)
- [SeaThru-NeRF: Neural Radiance Fields in Scattering Media](https://mlsanity.com/paper/2304.07743/) (2023)
- [InstantSplat: Sparse-view Gaussian Splatting in Seconds](https://mlsanity.com/paper/2403.20309/) (2024)
- [Underwater Ranker: Learn Which Is Better and How to Be Better](https://mlsanity.com/paper/2208.06857/) (2022)
- [WaterSplatting: Fast Underwater 3D Scene Reconstruction Using Gaussian Splatting](https://mlsanity.com/paper/2408.08206/) (2024)
- [SeaSplat: Representing Underwater Scenes with 3D Gaussian Splatting and a Physically Grounded Image Formation Model](https://mlsanity.com/paper/2409.17345/) (2024)
- [WaterNeRF: Neural Radiance Fields for Underwater Scenes](https://mlsanity.com/paper/2209.13091/) (2022)
- [FLSea: Underwater Visual-Inertial and Stereo-Vision Forward-Looking Datasets](https://mlsanity.com/paper/2302.12772/) (2023)
- [Real-Time Dense 3D Mapping of Underwater Environments](https://mlsanity.com/paper/2304.02704/) (2023)
- [RecGS: Removing Water Caustic with Recurrent Gaussian Splatting](https://mlsanity.com/paper/2407.10318/) (2024)
- [3R-GS: Best Practice in Optimizing Camera Poses Along with 3DGS](https://mlsanity.com/paper/2504.04294/) (2025)
- [Global Structure-from-Motion Meets Feedforward Reconstruction](https://mlsanity.com/paper/2605.26103/) (2026)
- [Plenodium: UnderWater 3D Scene Reconstruction with Plenoptic Medium Representation](https://mlsanity.com/paper/2505.21258/) (2025)
- [Refractive COLMAP: Refractive Structure-from-Motion Revisited](https://mlsanity.com/paper/2403.08640/) (2024)
- [Universal Beta Splatting](https://mlsanity.com/paper/2510.03312/) (2025)
- [OceanSplat: Object-aware Gaussian Splatting with Trinocular View Consistency for Underwater Scene Reconstruction](https://mlsanity.com/paper/2601.04984/) (2026)
- [Dark3R: Learning Structure from Motion in the Dark](https://mlsanity.com/paper/2603.05330/) (2026)
- [Camera Pose Refinement via 3D Gaussian Splatting](https://mlsanity.com/paper/2508.17876/) (2025)

## Built on by (most cited first, 1 of 1)

- [Image-Space Refraction Correction for Underwater 3D Reconstruction: Warping Flat-Port Views into Pinhole Perspective](https://mlsanity.com/paper/2610.07788/) (2026)

## Abstract (arXiv)

We propose Swimm3R, a unified framework that combines medium-aware structure-from-motion (SfM) with Underwater Beta Splatting to address scattering- and attenuation-induced failures in underwater 3D reconstruction. Swimm3R distills in-air geometric priors into a feed-forward backbone and uses a physics head to regress underwater image-formation parameters, camera poses, and restored point clouds. Additionally, we introduce Underwater Beta Splatting, which extends Gaussian splatting with Beta primitives and scattering-aware geometric gradients for stable underwater geometry representation. We further establish the Barbados underwater video dataset to demonstrate the effectiveness of our method in challenging underwater environments. On this dataset, Swimm3R robustly recovers underwater scene structure under challenging scattering conditions, yielding coherent seafloor geometry. Using these predicted point clouds, the proposed Underwater Beta Splatting improves average PSNR by 1.47 dB over WaterSplatting while increasing downstream localization performance by 2.0 and 2.4 percentage points in RRA@15 and RTA@15, respectively.